Pengenalan Jenis Daun Jambu Biji Menggunakan CNN MobileNetV2
DOI:
https://doi.org/10.29407/m2f6fh81Abstract
Identifikasi jenis jambu biji berdasarkan daun masih sering dilakukan secara manual dan bergantung pada pengamatan visual, sehingga berpotensi menimbulkan kesalahan terutama pada jenis daun yang memiliki kemiripan bentuk dan pola tulang daun. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi jenis daun jambu biji menggunakan metode Convolutional Neural Network dengan arsitektur MobileNetV2. Dataset yang digunakan terdiri dari empat kelas, yaitu jambu biji kristal merah, jambu varigata, jambu biji australia, dan jambu biji sukun dengan total 2000 citra. Proses penelitian meliputi preprocessing, augmentasi data, pelatihan model, serta evaluasi menggunakan metrik accuracy, precision, recall, dan F1-score. Selain itu, sistem dilengkapi dengan mekanisme open set recognition untuk mengidentifikasi citra yang bukan termasuk daun jambu. Hasil pengujian menunjukkan bahwa model mampu mencapai akurasi sebesar 0,99 dengan nilai evaluasi yang tinggi pada seluruh kelas. Hal ini menunjukkan bahwa MobileNetV2 mampu mengklasifikasikan citra daun jambu biji dengan baik dan dapat digunakan dalam sistem berbasis web.
Keywords:
CNN, klasifikasi citra, MobileNetV2, daun jambu biji, deep learning##plugins.themes.default.displayStats.downloads##
References
[1] T. Approach and Z. Leonowicz, “Identification of Plant-Leaf Diseases Using CNN and,”
2021.
[2] W. B. Demilie, “Plant disease detection and classification techniques : a comparative
study of the performances,” J. Big Data, 2024, doi: 10.1186/s40537-023-00863-9.
[3] M. Salman et al., “Heliyon IndoHerb : Indonesia medicinal plants recognition using
transfer learning and deep learning,” Heliyon, vol. 10, no. 23, p. e40606, 2024, doi:
10.1016/j.heliyon.2024.e40606.
[4] B. Dey, J. Ferdous, R. Ahmed, and J. Hossain, “Heliyon Assessing deep convolutional
neural network models and their comparative performance for automated medicinal
plant identification from leaf images,” Heliyon, vol. 10, no. 1, p. e23655, 2024, doi:
10.1016/j.heliyon.2023.e23655.
[5] L. Falaschetti, L. Manoni, D. Di, D. Pau, V. Tomaselli, and C. Turchetti, “HardwareX
A CNN-based image detector for plant leaf diseases classification,” HardwareX, vol. 12,
p. e00363, 2022, doi: 10.1016/j.ohx.2022.e00363.
[6] A. S. Paymode and V. B. Malode, “Arti fi cial Intelligence in Agriculture Transfer
Learning for Multi-Crop Leaf Disease Image Classi fi cation using Convolutional Neural
Network VGG,” Artif. Intell. Agric., vol. 6, pp. 23–33, 2022, doi:
10.1016/j.aiia.2021.12.002.
[7] T. Open and A. Journal, “Classification of Various Plant Leaf Disease Using Pretrained
Convolutional Neural Network On Imagenet,” pp. 1–15, 2024, doi:
10.2174/0118743315305194240408034912.
[8] B. Bharadwaj, A. Mishra, and S. Bharadwaj, “Transfer learning-based CNN models for
plant species identification using leaf venation patterns,” arXiv Prepr. arXiv2509.03729,
pp. 1–19, 2025.
[9] S. Auliani, D. Indra, and F. Umar, “Herbal Leaf Classification Using Convolutional
Neural Network ( CNN ) Method With VGG16 Architecture,” vol. 10, no. 2, 2026.
[10] S. Salsabila and A. Suharso, “Comparison of Deep Learning Architectures in Identifying
Types of Medicinal Plant Leaf Images,” vol. 8, no. 1, pp. 39–46, 2024.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
